© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242525
    Prev
    Next
    INDEX
    Explanations

    is divided divided are seen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nabíz
    0.38
    Vx
    0.35
     анд
    0.35
     ደ
    0.34
     analysing
    0.34
    Purg
    0.34
     Dementia
    0.34
     Aidan
    0.34
    訛
    0.34
    ISSION
    0.34
    POSITIVE LOGITS
     nore
    0.46
    hele
    0.41
    mos
    0.37
     newly
    0.37
    愭
    0.36
     novel
    0.36
     νο
    0.36
    inu
    0.35
     new
    0.35
     Tent
    0.35
    Activations Density 0.001%

    No Known Activations